© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105577
    Prev
    Next
    INDEX
    Explanations

    encourage frivolous, Kelly told

    np_acts-logits-general · gemini-2.5-flash-lite

    omit / optional elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    De
    0.50
    Ra
    0.46
    Tous
    0.45
    ati
    0.45
    凄
    0.43
    Da
    0.43
    Pa
    0.43
    War
    0.43
    Durante
    0.42
    wife
    0.42
    POSITIVE LOGITS
     kinderen
    0.54
    ಳ್
    0.53
     hogy
    0.52
    孩子
    0.50
    ම්භ
    0.49
    <unused713>
    0.49
     jongens
    0.47
     edades
    0.47
     zouden
    0.47
     incluindo
    0.47
    Activations Density 0.001%

    No Known Activations