© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 9658
    Prev
    Next
    INDEX
    Explanations

    whiskers made of spaghetti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consideration
    0.46
    ूं
    0.46
    Inflater
    0.45
    вно
    0.44
    壱
    0.44
    अल
    0.43
    wehr
    0.43
     punct
    0.43
    UAL
    0.42
    вле
    0.42
    POSITIVE LOGITS
     साइट
    0.51
    the
    0.51
     جان
    0.46
     nematode
    0.44
    nut
    0.43
    dana
    0.43
    bts
    0.43
    機
    0.43
     ब्रिटेन
    0.41
    田中
    0.41
    Activations Density 0.122%

    No Known Activations