© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7446
    Prev
    Next
    INDEX
    Explanations

    entity identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Ⴀ
    0.78
     väč
    0.74
    niejszych
    0.74
    Leadership
    0.73
    מיד
    0.70
    Registro
    0.69
    𒄩
    0.69
    𒊕
    0.69
    Throughout
    0.69
     elaborar
    0.68
    POSITIVE LOGITS
     someone
    1.15
     malicious
    0.89
     somebody
    0.86
     or
    0.86
     Someone
    0.78
    someone
    0.77
     something
    0.75
     anyone
    0.73
     alguien
    0.71
     nefarious
    0.69
    Activations Density 0.000%

    No Known Activations