© 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. 62198
    Prev
    Next
    INDEX
    Explanations

    mother and phrases about mothers

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

    mother in taboo scenarios

    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
    on
    0.89
    리
    0.74
    ພວກເຮົາ
    0.72
    ۸
    0.71
     irá
    0.69
    يق
    0.69
    는
    0.69
    ８
    0.68
     els
    0.66
    have
    0.66
    POSITIVE LOGITS
    -
    0.63
     for
    0.59
    น้อย
    0.59
     mother
    0.59
    preneur
    0.59
    /
    0.59
     PNS
    0.57
    Vater
    0.56
     remplacement
    0.56
    impanan
    0.56
    Activations Density 0.053%

    No Known Activations