© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148963
    Prev
    Next
    INDEX
    Explanations

    greeting, Doctor, JavaScript, Silas, spread

    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_29_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
    lmp
    0.85
     optically
    0.82
    Ϥ
    0.82
    pyrid
    0.80
    MSC
    0.79
    myData
    0.78
    訢
    0.76
    <unused1917>
    0.76
     DMP
    0.75
     mtDNA
    0.74
    POSITIVE LOGITS
    _:
    0.91
    %;
    0.89
    хова
    0.80
    %:
    0.80
    레스
    0.78
    ė
    0.77
     fame
    0.76
     एव
    0.76
    names
    0.75
     names
    0.74
    Activations Density 0.000%

    No Known Activations