© 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. 98480
    Prev
    Next
    INDEX
    Explanations

    economic or political entities

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

    Gemma or platform developments

    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
    0.52
     backlash
    0.45
    iters
    0.43
     Notice
    0.42
     a
    0.41
    mert
    0.41
     backlog
    0.40
    pollution
    0.40
    e
    0.40
    }(\
    0.40
    POSITIVE LOGITS
     limitada
    0.56
    क्राम
    0.55
    वाइड
    0.55
    )،
    0.54
    धपुर
    0.52
    护
    0.51
    )。
    0.50
    noduch
    0.50
     apari
    0.49
     ruido
    0.49
    Activations Density 0.000%

    No Known Activations