© 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. 195542
    Prev
    Next
    INDEX
    Explanations

    ebook free

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

    chicken and thighs

    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
     Dina
    0.44
     Pamela
    0.43
    NJ
    0.42
    Sue
    0.41
    Tweets
    0.41
    />
    0.41
    Ya
    0.41
    Evaluate
    0.41
     आईएफ
    0.40
    Effects
    0.40
    POSITIVE LOGITS
     앞에
    0.55
     위에
    0.54
    書店
    0.50
     propag
    0.45
    階段
    0.45
     CaO
    0.43
    idable
    0.43
    준
    0.43
     준
    0.42
     맞는
    0.42
    Activations Density 0.000%

    No Known Activations