© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40428
    Prev
    Next
    INDEX
    Explanations

    incorrect parameters, behavior, result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     It
    -3.09
    In
    -2.94
    We
    -2.67
    =
    -2.64
                
    -2.63
    A
    -2.61
    If
    -2.44
    </td>
    -2.23
     But
    -2.23
    -
    -2.20
    POSITIVE LOGITS
    .
    2.81
    ='')
    2.61
    翃
    2.53
    を始め
    2.50
    齜
    2.48
    <<<<<<<
    2.41
    が大
    2.38
    酲
    2.36
    尨
    2.34
    鰾
    2.31
    Activations Density 0.004%

    No Known Activations