© 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. 100292
    Prev
    Next
    INDEX
    Explanations

    place names and continuations

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

    fits the

    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
     Raised
    0.41
    飕
    0.41
     নারায়ণ
    0.41
     kullanarak
    0.41
     Slice
    0.40
     Roh
    0.39
     Husky
    0.39
     называется
    0.39
    btnUn
    0.39
    뿔
    0.38
    POSITIVE LOGITS
     elit
    0.47
    conn
    0.46
     imposs
    0.45
    mc
    0.44
    ONENT
    0.44
    ODES
    0.43
    ANCES
    0.43
     गुणा
    0.43
     dominions
    0.43
    ;&#
    0.42
    Activations Density 0.000%

    No Known Activations