© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110574
    Prev
    Next
    INDEX
    Explanations

    evidence-based concepts

    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_34/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
    werth
    -0.82
    paz
    -0.82
    étro
    -0.78
    ^{-\
    -0.77
    AtIndex
    -0.77
    stuffs
    -0.77
     StringIO
    -0.76
     sklo
    -0.76
    甸
    -0.75
    ٸ
    -0.75
    POSITIVE LOGITS
     evidence
    3.13
    evidence
    2.42
     Evidence
    2.41
    Evidence
    2.28
     evidenced
    2.16
     based
    2.11
     EVIDENCE
    1.87
     informed
    1.84
     backed
    1.82
    BASED
    1.82
    Activations Density 0.056%

    No Known Activations