© 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. 180960
    Prev
    Next
    INDEX
    Explanations

    failing to, crochet, candles, credit, Trustee, receiver

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

    static states, uncertainty, watching

    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
    etrot
    0.49
    }}=-\
    0.48
    }}-\
    0.46
    윅
    0.46
    🍽
    0.45
    ickou
    0.45
    வித்து
    0.45
    ick
    0.45
    })=\
    0.45
     期
    0.45
    POSITIVE LOGITS
     critical
    0.52
     kefir
    0.52
     %
    0.50
     crítica
    0.49
     kait
    0.48
     very
    0.47
     foarte
    0.46
     oxygen
    0.46
     väldigt
    0.46
     París
    0.46
    Activations Density 0.001%

    No Known Activations