© 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. 217024
    Prev
    Next
    INDEX
    Explanations

    payment or check

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

    explores themes of intimacy and romance

    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
     vectơ
    0.46
    片段
    0.45
    कालीन
    0.44
    $\\
    0.44
    眙
    0.44
     Infantil
    0.43
    ון
    0.43
     cỡ
    0.43
    聩
    0.42
     뛰
    0.42
    POSITIVE LOGITS
     shrines
    0.46
     gleichen
    0.45
     acceptable
    0.44
    acceptable
    0.43
     meinem
    0.43
     suicides
    0.43
     enclosures
    0.42
     temples
    0.42
     dezelfde
    0.42
     angelic
    0.42
    Activations Density 0.000%

    No Known Activations