© 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. 121862
    Prev
    Next
    INDEX
    Explanations

    advise friend future

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

    specific phrasing about sensitive topics

    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
     décide
    0.47
     puissance
    0.44
     encoder
    0.43
     décider
    0.42
     décision
    0.42
     pêche
    0.42
     decid
    0.41
    ο
    0.41
     pét
    0.41
    قر
    0.40
    POSITIVE LOGITS
    es
    0.59
    i
    0.57
    eit
    0.55
    eb
    0.50
    eng
    0.50
    iapan
    0.49
    blichen
    0.48
    en
    0.47
    ে
    0.47
    az
    0.47
    Activations Density 0.000%

    No Known Activations