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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31546
    Prev
    Next
    INDEX
    Explanations

    life after death, tube insertion, health risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
     diğer
    0.92
     другими
    0.92
     sebepler
    0.88
     sauerkraut
    0.87
     profusely
    0.86
    ﺹ
    0.86
     przechowy
    0.86
    ﺽ
    0.86
     tekst
    0.85
     neem
    0.83
    POSITIVE LOGITS
    গত
    0.75
    <
    0.68
     nevoie
    0.66
    czna
    0.65
    кат
    0.64
    기
    0.64
    czne
    0.63
    的天
    0.63
    знав
    0.63
    тивна
    0.63
    Activations Density 0.000%

    No Known Activations