© 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. 44475
    Prev
    Next
    INDEX
    Explanations

    Here's how

    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
     frutto
    1.36
    ਸ
    1.33
    து
    1.25
    ە
    1.22
    న్
    1.19
    בח
    1.19
    TempBuffer
    1.17
    쐞
    1.17
    ě
    1.16
    resultado
    1.15
    POSITIVE LOGITS
     LO
    0.94
     VO
    0.88
     Killer
    0.87
     questionnaires
    0.87
     OAS
    0.86
     Hash
    0.85
     Getter
    0.84
    kins
    0.83
     boundaries
    0.83
    ,
    0.83
    Activations Density 0.029%

    No Known Activations