© 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. 6580
    Prev
    Next
    INDEX
    Explanations

    multiplied, overall tone, currencies

    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
    твы
    0.86
     ờ
    0.86
    ۾
    0.86
     narcissistic
    0.85
     compreender
    0.85
     subcellular
    0.84
    coelastic
    0.84
    疠
    0.82
    oxidase
    0.82
     tachycardia
    0.82
    POSITIVE LOGITS
    ی
    0.92
    la
    0.84
    ll
    0.80
    )
    0.78
    ne
    0.76
    Ch
    0.75
    न
    0.72
    lo
    0.71
     ‘
    0.69
    Am
    0.68
    Activations Density 0.000%

    No Known Activations