© 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. 44833
    Prev
    Next
    INDEX
    Explanations

    shrug

    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
    ই
    1.29
    이나
    1.21
    +
    1.11
    *
    1.10
    ใด
    1.09
    உ
    1.09
    การ
    1.05
    বা
    1.05
    பு
    1.05
    ಕ
    1.05
    POSITIVE LOGITS
    phia
    1.20
     solvents
    1.17
     ejercicios
    1.09
     parishes
    1.09
     potencia
    1.08
    ases
    1.05
    িল
    1.05
     bushings
    1.05
     methods
    1.03
    acles
    1.02
    Activations Density 0.000%

    No Known Activations