Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165831
    Prev
    Next
    INDEX
    Explanations

    humanoid descriptions

    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_40_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
     Spectre
    0.38
    いません
    0.38
     maio
    0.37
     থানা
    0.37
     thẩm
    0.36
    (',');
    0.36
     colect
    0.36
     novelty
    0.35
    柒
    0.35
     beloved
    0.35
    POSITIVE LOGITS
    phs
    0.42
     entr
    0.41
    ካል
    0.40
    htp
    0.39
    lád
    0.39
     lont
    0.39
     හැ
    0.38
     buts
    0.38
    ellidos
    0.37
    olia
    0.37
    Activations Density 0.000%

    No Known Activations