© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220980
    Prev
    Next
    INDEX
    Explanations

    on a

    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
     enormes
    0.48
     cytologic
    0.45
     Hygien
    0.44
     ्
    0.44
    تمر
    0.43
    媾
    0.42
     enorme
    0.41
     নির্মম
    0.41
    huge
    0.40
     instances
    0.40
    POSITIVE LOGITS
    ξ
    0.42
    ித்த
    0.38
     θ
    0.38
    क्स
    0.37
    ツ
    0.37
     बढ़ते
    0.37
    ப
    0.37
    κρα
    0.36
    水
    0.36
    κ
    0.36
    Activations Density 0.000%

    No Known Activations