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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42385
    Prev
    Next
    INDEX
    Explanations

    php code blocks

    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
    Sig
    0.45
     SIG
    0.42
     Sig
    0.39
    SIG
    0.39
    qiya
    0.38
    ⵕ
    0.38
    Mother
    0.38
     podr
    0.38
    voer
    0.37
    praw
    0.37
    POSITIVE LOGITS
     మరి
    0.42
     n
    0.40
     ((
    0.40
     ところ
    0.38
     Evaluate
    0.38
     因為
    0.37
    olymer
    0.37
     জলা
    0.37
    కుండా
    0.36
     evaluates
    0.36
    Activations Density 0.005%

    No Known Activations