© 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. 233157
    Prev
    Next
    INDEX
    Explanations

    cultural examples and applications

    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
    锜
    0.48
     expiration
    0.48
     disbursement
    0.48
     dispense
    0.47
     situate
    0.47
     réseau
    0.46
    That
    0.46
     refuse
    0.46
     gestione
    0.46
     što
    0.45
    POSITIVE LOGITS
    }(-\
    0.50
    cs
    0.50
     реги
    0.50
    }^{(\
    0.50
    aia
    0.48
    orant
    0.47
    స్వా
    0.47
    }(-
    0.45
    ."))
    0.45
    orpion
    0.45
    Activations Density 0.000%

    No Known Activations