© 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. 99604
    Prev
    Next
    INDEX
    Explanations

    measuring space and dimensions

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

    long reads or publications

    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
     outputs
    0.50
    output
    0.47
     output
    0.46
    高清
    0.45
     churn
    0.44
     どれ
    0.43
    原子炉
    0.43
    }^{(
    0.42
     অল্প
    0.42
    牷
    0.42
    POSITIVE LOGITS
    धे
    0.46
     impenetr
    0.43
    luğu
    0.42
     amiss
    0.42
     boyunca
    0.41
     merkezi
    0.41
    க்குப்
    0.41
     پیم
    0.41
    급
    0.41
    ඈ
    0.41
    Activations Density 0.000%

    No Known Activations