© 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. 70178
    Prev
    Next
    INDEX
    Explanations

    daily or next day

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

    accumulates summarization

    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
     allergens
    0.61
    _
    0.54
    is
    0.53
    ap
    0.53
    alist
    0.52
    odas
    0.52
    ad
    0.49
    ando
    0.49
     discapac
    0.49
    apat
    0.49
    POSITIVE LOGITS
     Subjects
    0.48
     Sebab
    0.48
     Kamb
    0.45
     Übers
    0.45
     :#
    0.45
     Manager
    0.44
     Ce
    0.44
     Denk
    0.44
     Це
    0.44
    事项
    0.44
    Activations Density 0.000%

    No Known Activations