© 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. 120512
    Prev
    Next
    INDEX
    Explanations

    either or all, sure to, fact

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

    threats, RFCs, questions, supremacists

    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
    MIC
    0.45
     mimic
    0.44
    giveness
    0.44
     MIC
    0.42
     स्थानिक
    0.42
    NU
    0.42
    ድ
    0.41
    झ
    0.41
     Mik
    0.41
     shortening
    0.41
    POSITIVE LOGITS
     উপস
    0.47
     мое
    0.46
     chatted
    0.46
     allegedly
    0.46
     conjectured
    0.46
     airson
    0.45
    伈
    0.45
     invalidated
    0.45
    сить
    0.44
     вроде
    0.44
    Activations Density 0.000%

    No Known Activations