© 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. 113278
    Prev
    Next
    INDEX
    Explanations

    specific months or dates

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

    grammatically correct details

    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
    }.
    0.56
    apy
    0.52
    ].
    0.52
    ya
    0.49
    to
    0.48
    emit
    0.47
     Column
    0.45
    mask
    0.43
    item
    0.43
     emitted
    0.43
    POSITIVE LOGITS
    اید
    0.57
    ڈیو
    0.56
    굿
    0.53
    منا
    0.50
    ジア
    0.50
    شوف
    0.50
    浻
    0.50
    خد
    0.49
    يد
    0.49
    랜드
    0.49
    Activations Density 0.000%

    No Known Activations