© 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. 97086
    Prev
    Next
    INDEX
    Explanations

    slain from, asked him, alone terminal, value of, close by, violation of, heaven ”

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

    standalone judge rebels flaws paced

    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
    fwrite
    0.46
    ısını
    0.42
    礼
    0.42
    னை
    0.42
    徙
    0.42
    ிரி
    0.41
    ᒫ
    0.41
    δει
    0.40
    醚
    0.40
    también
    0.40
    POSITIVE LOGITS
     zonder
    0.49
     glamorous
    0.46
     Downtown
    0.46
     typu
    0.46
     voor
    0.45
     जानिए
    0.45
     frantic
    0.44
     glamour
    0.43
    0.43
     مدينة
    0.43
    Activations Density 0.000%

    No Known Activations