© 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. 55672
    Prev
    Next
    INDEX
    Explanations

    reference to, with living, elegant inspirational

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

    artificially inflates the price

    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
    戽
    0.49
    Rear
    0.46
    BoardManager
    0.44
     Рі
    0.43
     проєкту
    0.43
    據
    0.43
     Saviour
    0.42
     portas
    0.42
    睪
    0.42
    阌
    0.41
    POSITIVE LOGITS
    before
    0.50
    append
    0.47
    conditional
    0.46
    shape
    0.46
     before
    0.46
     சிறு
    0.46
    sec
    0.45
    plicate
    0.45
    finish
    0.45
    color
    0.45
    Activations Density 0.000%

    No Known Activations