© 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. 217026
    Prev
    Next
    INDEX
    Explanations

    fertility and parenthood

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

    content within brackets

    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
    cand
    0.47
    Cand
    0.45
     vegetarian
    0.43
    暴
    0.43
     الصح
    0.42
    矛盾
    0.42
     cand
    0.41
     boolean
    0.41
    owness
    0.41
    禟
    0.40
    POSITIVE LOGITS
     travaux
    0.57
    ﺸ
    0.57
    lée
    0.52
    사이트
    0.50
     compét
    0.49
     dispara
    0.49
     ዓይ
    0.48
     ძალი
    0.48
     implique
    0.48
     opérations
    0.48
    Activations Density 0.000%

    No Known Activations