© 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. 16700
    Prev
    Next
    INDEX
    Explanations

    posted on dates

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

    built with images

    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
    ofi
    0.37
     विशेष
    0.36
    fte
    0.36
    betrieb
    0.35
    setting
    0.35
    öhn
    0.35
    𝚎
    0.35
    ûn
    0.34
     पुष्पा
    0.34
    oport
    0.34
    POSITIVE LOGITS
     egli
    0.42
     udało
    0.40
     professe
    0.39
     daughter
    0.39
     élevée
    0.39
     Daughter
    0.38
     passionately
    0.38
     princesses
    0.38
     Outcome
    0.37
     viagens
    0.37
    Activations Density 0.000%

    No Known Activations