© 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. 195122
    Prev
    Next
    INDEX
    Explanations

    personal needs and details

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

    learned to perform tasks

    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
     until
    0.55
     someone
    0.52
     proxy
    0.52
     any
    0.50
     itself
    0.50
     initially
    0.48
     a
    0.47
     customers
    0.47
     village
    0.46
     Until
    0.46
    POSITIVE LOGITS
     dangere
    0.56
     நாடுக
    0.54
    ımız
    0.52
    လည်း
    0.52
     верши
    0.51
     பூம
    0.51
    𝐳
    0.50
    řeb
    0.50
    ctrine
    0.49
     يون
    0.49
    Activations Density 0.000%

    No Known Activations