© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82370
    Prev
    Next
    INDEX
    Explanations

    disclaimers and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interactive
    0.46
    \|$.
    0.45
     বায়
    0.42
    Kana
    0.40
     supernatant
    0.40
     excludes
    0.40
    HIS
    0.40
     >>=
    0.39
     পিতা
    0.39
    メール
    0.39
    POSITIVE LOGITS
     infamous
    0.47
     (
    0.46
     goog
    0.46
     vanqu
    0.44
     Flyers
    0.44
     slain
    0.44
     (%)
    0.43
     Sack
    0.43
    کی
    0.42
    經常
    0.42
    Activations Density 0.001%

    No Known Activations