© 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. 83962
    Prev
    Next
    INDEX
    Explanations

    couple damaged books will now stop

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

    defining specific nuances

    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
    กรา
    0.55
    এফ
    0.50
    藩
    0.49
    Ꮞ
    0.49
    ⸙
    0.49
    申請
    0.49
     поддержки
    0.49
    𒈪
    0.48
    制的
    0.48
    樾
    0.48
    POSITIVE LOGITS
    nin
    0.56
     with
    0.52
    ned
    0.51
    nai
    0.50
    ns
    0.50
    :
    0.50
    re
    0.49
    nge
    0.48
    sc
    0.48
    nz
    0.48
    Activations Density 0.000%

    No Known Activations