© 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-16K
    7. 5403
    Prev
    Next
    INDEX
    Explanations

    or alternative

    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_16k_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
    ili
    0.40
    इस
    0.39
    ５
    0.39
    別途
    0.38
    ტიკ
    0.37
    ਦੀ
    0.36
    也沒有
    0.36
    講
    0.36
    BUT
    0.36
    केवल
    0.36
    POSITIVE LOGITS
     অথবা
    0.47
    以及
    0.47
     oraz
    0.45
     तसेच
    0.43
     &/
    0.43
     কিংবা
    0.43
     તથા
    0.42
     以及
    0.42
     and
    0.42
     మరియు
    0.41
    Activations Density 0.225%

    No Known Activations