Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4016
    Prev
    Next
    INDEX
    Explanations

    band

    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
    od
    2.27
    ij
    2.17
    iją
    1.88
     bientôt
    1.80
     해당하는
    1.77
    be
    1.77
    ન
    1.72
     
    1.71
    isión
    1.70
    và
    1.70
    POSITIVE LOGITS
    ان
    2.27
    াঙ্গীর
    2.06
    ীদ
    2.02
    ৫
    1.95
    ০
    1.92
    ोब
    1.91
    ۰
    1.85
    িং
    1.84
     waveguides
    1.84
    К
    1.84
    Activations Density 0.064%

    No Known Activations