© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1060
    Prev
    Next
    INDEX
    Explanations

    geographical locations, natural phenomena

    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_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
     ></
    0.91
     Issled
    0.80
    ių
    0.80
     Title
    0.78
     actomyosin
    0.78
    דים
    0.77
    <0x92>
    0.76
    ("~/
    0.76
    кера
    0.76
    esse
    0.75
    POSITIVE LOGITS
    f
    0.98
    m
    0.88
    てる
    0.85
     vitality
    0.83
    개가
    0.83
    y
    0.83
     siren
    0.82
    й
    0.82
    ュ
    0.80
     trabalh
    0.80
    Activations Density 0.001%

    No Known Activations