© 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. 228227
    Prev
    Next
    INDEX
    Explanations

    investigate a

    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
    ]
    0.55
    /
    0.53
    ING
    0.51
    )
    0.50
    '
    0.49
     hill
    0.47
     erect
    0.47
     economically
    0.46
    DR
    0.45
    ,
    0.44
    POSITIVE LOGITS
     Measurements
    0.50
     Antibodies
    0.50
     ब्रेक
    0.47
     diversité
    0.47
    inherited
    0.47
     Perspectives
    0.47
     Некоторые
    0.46
    媑
    0.46
     गायब
    0.46
     Embrace
    0.46
    Activations Density 0.000%

    No Known Activations