© 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. 197641
    Prev
    Next
    INDEX
    Explanations

    next month or for generations

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

    Mersenne primes or gods decree

    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
    espoir
    0.53
    oeuvre
    0.50
    irge
    0.47
     jedem
    0.46
    劦
    0.46
    rable
    0.45
    ర్య
    0.45
    公正
    0.45
     масштаб
    0.44
    воре
    0.44
    POSITIVE LOGITS
     latch
    0.44
    ן
    0.43
    ALT
    0.43
     raczej
    0.42
     REST
    0.41
    AL
    0.41
    רה
    0.41
     לג
    0.40
    ংশের
    0.39
     TIL
    0.39
    Activations Density 0.000%

    No Known Activations