© 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. 194039
    Prev
    Next
    INDEX
    Explanations

    due to

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

    pros and cons of items

    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
     irrelevant
    0.48
    *
    0.46
     by
    0.44
     infiltrating
    0.44
    Grad
    0.43
     incl
    0.41
    Key
    0.41
    Role
    0.41
    Retro
    0.41
     waktu
    0.40
    POSITIVE LOGITS
     coprodu
    0.52
     CONSULT
    0.51
     Seç
    0.51
    έα
    0.50
     CH
    0.50
     vadati
    0.49
    म
    0.49
     Acción
    0.48
    ‌്
    0.48
     Bây
    0.48
    Activations Density 0.000%

    No Known Activations