© 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. 135146
    Prev
    Next
    INDEX
    Explanations

    file association errors

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

    possible, necessary, or agent

    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
    from
    0.52
    al
    0.51
     used
    0.49
    <start_of_image>
    0.46
     NON
    0.45
     matrices
    0.44
    Ni
    0.44
     RESER
    0.44
    <strong>
    0.44
    Bi
    0.43
    POSITIVE LOGITS
     possíveis
    0.52
     वेरी
    0.50
    χής
    0.49
     mögliche
    0.49
    ěř
    0.49
     مدينه
    0.49
     vykon
    0.48
    妸
    0.48
     ശ
    0.47
    ător
    0.47
    Activations Density 0.000%

    No Known Activations