© 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. 150563
    Prev
    Next
    INDEX
    Explanations

    .za / Mum

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

    Anima/Animus or feminine side

    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
    T
    0.46
    M
    0.46
    P
    0.45
     ;
    0.43
     unassuming
    0.42
    eds
    0.42
    LOST
    0.42
     ignorance
    0.42
    D
    0.42
    R
    0.41
    POSITIVE LOGITS
    ié
    0.50
    AssetDiscovery
    0.49
    ાન
    0.47
     thisTrack
    0.46
    PatientR
    0.44
    iénd
    0.44
    iya
    0.43
    烁
    0.43
    哳
    0.43
    loadNpm
    0.43
    Activations Density 0.002%

    No Known Activations