© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152483
    Prev
    Next
    INDEX
    Explanations

    business, selling, therapies

    np_acts-logits-general · gemini-2.5-flash-lite

    structured lists and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arono
    0.54
    atonin
    0.53
    ين
    0.52
    氛围
    0.51
    т
    0.50
    ার
    0.50
    🍥
    0.50
    سین
    0.49
    ामु
    0.49
    функ
    0.49
    POSITIVE LOGITS
    omb
    0.45
    isi
    0.45
    </i>
    0.45
    vDash
    0.44
    iliation
    0.44
     d
    0.43
    endent
    0.42
     पढ़कर
    0.42
    上半年
    0.42
    idel
    0.41
    Activations Density 0.000%

    No Known Activations