© 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. 225962
    Prev
    Next
    INDEX
    Explanations

    permissions and system administration

    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
    VerFile
    0.45
     پیسہ
    0.45
    ९
    0.44
     corrosive
    0.44
    ('.')
    0.43
    乀
    0.43
     destructive
    0.42
     خطوات
    0.42
    齢
    0.42
     بالح
    0.41
    POSITIVE LOGITS
     Permission
    0.49
    튜브
    0.49
    }}
    0.48
    𝕄
    0.47
    মির
    0.46
     Merid
    0.45
    面上
    0.45
     Aplic
    0.45
    oodles
    0.44
    沙漠
    0.44
    Activations Density 0.001%

    No Known Activations