© 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. 74566
    Prev
    Next
    INDEX
    Explanations

    updated on, hidden, floor, MO firms, Keep reading

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

    not just, but rather

    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
     我們
    0.51
     問
    0.51
     ברי
    0.50
     同じ
    0.50
     週
    0.50
     特に
    0.49
     ແລະ
    0.49
    ]?.
    0.49
     మర
    0.49
     говорил
    0.48
    POSITIVE LOGITS
     ascends
    0.51
    </code>
    0.48
    いです
    0.47
    ........
    0.46
    lil
    0.45
    rose
    0.44
     sentiment
    0.44
    refresh
    0.44
    ag
    0.44
     lucrative
    0.44
    Activations Density 0.001%

    No Known Activations