© 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. 199526
    Prev
    Next
    INDEX
    Explanations

    fully permitted, online reviews, since sweep

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

    digital signature

    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
    }=(\
    0.48
    arg
    0.44
     evaluations
    0.44
     heifers
    0.43
    ኝነት
    0.43
     soundtracks
    0.43
    }=\{\
    0.42
     factions
    0.42
    cX
    0.42
    edad
    0.41
    POSITIVE LOGITS
    깔
    0.49
     выборе
    0.47
     занимает
    0.46
     Lah
    0.44
    प्ला
    0.43
     Após
    0.43
     வேண்டும்
    0.43
     Conch
    0.42
     ক্লান্ত
    0.42
     ausgezeichnet
    0.41
    Activations Density 0.001%

    No Known Activations