© 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. 3254
    Prev
    Next
    INDEX
    Explanations

    blank, Ask, size

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

    how to learn or get information

    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
    EventArgs
    0.46
     accidents
    0.45
    жает
    0.45
     impedance
    0.43
     ulcers
    0.43
     tumeurs
    0.42
    捗
    0.42
     ulcer
    0.41
    檗
    0.41
     impairments
    0.41
    POSITIVE LOGITS
     Ask
    0.49
     Harrison
    0.47
     Owned
    0.46
     ask
    0.46
     Hope
    0.46
     LET
    0.45
     Lay
    0.43
     Let
    0.43
     Free
    0.42
     AL
    0.42
    Activations Density 0.000%

    No Known Activations