© 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. 201233
    Prev
    Next
    INDEX
    Explanations

    lists, tables, throughout

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

    explaining concepts with bullet points

    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
     newsc
    0.44
    kami
    0.44
     анима
    0.43
     an
    0.42
     PROGRAMS
    0.42
     hypothesized
    0.41
    윈
    0.41
     பண
    0.41
     உயர
    0.40
     Oph
    0.40
    POSITIVE LOGITS
    '',
    0.59
    ’’
    0.55
    /<
    0.51
    ''
    0.49
    *',
    0.49
    ''}
    0.48
    MaxPooling
    0.47
    *
    0.47
    '''
    0.47
    lastval
    0.47
    Activations Density 0.000%

    No Known Activations