© 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. 50
    Prev
    Next
    INDEX
    Explanations

    phrases forming specific concepts

    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
    1
    0.44
    2
    0.42
    4
    0.42
    6
    0.39
    9
    0.39
    5
    0.38
    7
    0.37
    A
    0.36
    H
    0.33
    3
    0.33
    POSITIVE LOGITS
     junkie
    0.37
     ridicul
    0.36
     jugar
    0.36
     jugador
    0.36
     giocatore
    0.36
     pelea
    0.35
     banter
    0.35
     वोट
    0.34
     hijab
    0.34
     jogador
    0.34
    Activations Density 0.000%

    No Known Activations