© 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. 4108
    Prev
    Next
    INDEX
    Explanations

    router configuration

    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
    a
    1.84
    忥
    1.60
     rechaz
    1.56
     don
    1.48
    ać
    1.47
    ⤦
    1.47
     striées
    1.46
    chutz
    1.46
     necessariamente
    1.46
    aient
    1.45
    POSITIVE LOGITS
    ون
    1.80
    ோ
    1.63
    1.62
    ό
    1.62
    ات
    1.57
    িক
    1.52
    ാ
    1.52
    IZ
    1.50
    ता
    1.49
    ों
    1.48
    Activations Density 0.001%

    No Known Activations