© 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. 187683
    Prev
    Next
    INDEX
    Explanations

    contact followed by possessive or article

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

    information, data, needs

    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
    ォ
    0.51
     includ
    0.47
     commensurate
    0.46
    isFile
    0.45
    ié
    0.44
     edifice
    0.44
     choirs
    0.44
    ."
    0.43
    ^{-
    0.42
    }^{-
    0.42
    POSITIVE LOGITS
     Ante
    0.48
    ällä
    0.48
    your
    0.46
     Replies
    0.46
     Một
    0.45
     Når
    0.44
     Jeśli
    0.44
     रस
    0.44
     Sabemos
    0.43
    ົມ
    0.43
    Activations Density 0.001%

    No Known Activations