© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11411
    Prev
    Next
    INDEX
    Explanations

    this [specific noun]

    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_22/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
    を
    -1.55
    <bos>
    -1.54
     each
    -1.46
    与此同时
    -1.45
    これは
    -1.41
    そのため
    -1.41
    が
    -1.41
    ポイントは
    -1.40
    もあって
    -1.39
     of
    -1.38
    POSITIVE LOGITS
    為に
    1.63
    corrhi
    1.44
     huellas
    1.44
    を選択します
    1.38
    ようになって
    1.36
    えっ
    1.30
     burbujas
    1.30
     materialen
    1.26
    ようになります
    1.25
     škoda
    1.25
    Activations Density 0.034%

    No Known Activations