© 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. 227269
    Prev
    Next
    INDEX
    Explanations

    all, case, machine, voice, update, Colombo

    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
     wię
    0.61
     trochę
    0.53
    źdz
    0.52
    𝓵
    0.51
     トップ
    0.51
     പരിശ
    0.51
    ufieurs
    0.50
    Ɩ
    0.50
    それ
    0.50
     মডেল
    0.50
    POSITIVE LOGITS
     .
    0.50
    agr
    0.49
    udo
    0.48
    post
    0.48
     unde
    0.47
     what
    0.47
    vite
    0.46
    kv
    0.45
    md
    0.45
    jd
    0.44
    Activations Density 0.000%

    No Known Activations