© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162769
    Prev
    Next
    INDEX
    Explanations

    access, audit, or entrance

    np_acts-logits-general · gemini-2.5-flash-lite

    muscular actress, run in, retrieved classification, self-interested, quickly evolved, highest space, can fund, lighting designs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ',
    0.44
    IRED
    0.44
     lần
    0.43
    {'
    0.43
     Crawley
    0.42
    {
    0.42
    Anti
    0.41
    Auto
    0.41
    Alignment
    0.41
    ALIGN
    0.41
    POSITIVE LOGITS
     sadistic
    0.48
     می‌توانید
    0.47
    amini
    0.45
    扼
    0.45
     hegemony
    0.44
     त्यावर
    0.44
    rods
    0.44
     excuses
    0.43
     هون
    0.43
     करण्यासाठी
    0.43
    Activations Density 0.001%

    No Known Activations