© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84697
    Prev
    Next
    INDEX
    Explanations

    was going to verb

    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
    会导致
    -2.19
    ፝
    -1.88
    鉏
    -1.79
    zzlement
    -1.74
    ⧠
    -1.74
    erintah
    -1.65
    FFIX
    -1.63
    $-$
    -1.63
    ޏ
    -1.63
    橚
    -1.59
    POSITIVE LOGITS
     tetapi
    2.28
    .”
    1.77
    л
    1.66
     be
    1.56
    intah
    1.44
     graag
    1.44
     not
    1.41
    但
    1.38
    酌
    1.38
     详情
    1.37
    Activations Density 0.009%

    No Known Activations