© 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. 162644
    Prev
    Next
    INDEX
    Explanations

    requests for erasure

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

    protected property or assets

    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
     bushels
    0.41
     irrespective
    0.39
    ]
    0.39
     circle
    0.37
     Hooper
    0.37
     radial
    0.36
     Horner
    0.36
    ush
    0.35
    ynt
    0.35
     Raider
    0.35
    POSITIVE LOGITS
    濯
    0.48
    Über
    0.46
     lugar
    0.46
    ガラ
    0.46
    令和
    0.45
    旮
    0.45
    día
    0.45
    மாட்ட
    0.45
    ログイン
    0.44
    קום
    0.44
    Activations Density 0.002%

    No Known Activations