© 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. 233839
    Prev
    Next
    INDEX
    Explanations

    control ensures

    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
     Labrenzia
    0.51
    ডো
    0.48
     obiettivo
    0.48
     micrófono
    0.47
    💊
    0.47
    Ⲙ
    0.46
    ﮩ
    0.46
     त्यौ
    0.46
    🟩
    0.46
     realizzazione
    0.46
    POSITIVE LOGITS
    The
    0.50
     feudal
    0.50
     mortal
    0.48
     and
    0.48
    }
    0.46
     The
    0.46
     system
    0.44
    ))
    0.44
    e
    0.44
     master
    0.44
    Activations Density 0.001%

    No Known Activations