© 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. 199897
    Prev
    Next
    INDEX
    Explanations

    travel offers, damage resistant bacteria, lvl 2

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

    complex sentences and features

    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
    祺
    0.53
    comment
    0.42
    कश्मीर
    0.42
     Insulation
    0.42
     prefs
    0.42
     DSO
    0.41
    Forgery
    0.40
    تهي
    0.40
    ื
    0.40
    RSA
    0.39
    POSITIVE LOGITS
     pouces
    0.52
     iç
    0.51
     コン
    0.50
     went
    0.49
     высо
    0.48
     yoğun
    0.48
     পায়ের
    0.47
     `:`,
    0.47
     immensely
    0.47
     внутрен
    0.47
    Activations Density 0.000%

    No Known Activations