© 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. 173037
    Prev
    Next
    INDEX
    Explanations

    identifying specific items

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

    to identify something

    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
     on
    0.65
    ဆ
    0.61
     எழுத
    0.60
    ية
    0.59
     is
    0.59
    舏
    0.59
     ਨੂੰ
    0.57
    melding
    0.57
    奂
    0.57
     ဆ
    0.57
    POSITIVE LOGITS
    Identify
    1.23
     Identify
    1.05
    Identifying
    1.02
     Identifying
    1.02
    Ident
    0.99
    identify
    0.99
     identific
    0.95
     Ident
    0.89
    Identification
    0.89
     identify
    0.89
    Activations Density 0.057%

    No Known Activations