© 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. 11437
    Prev
    Next
    INDEX
    Explanations

    already followed by 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_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
     superb
    -2.31
     dando
    -2.28
    9
    -2.13
     marvelous
    -2.11
     efek
    -2.08
     realmente
    -2.06
     splendid
    -2.05
     crucial
    -2.02
     premiere
    -2.00
     &
    -1.97
    POSITIVE LOGITS
    '
    2.47
    愎
    2.22
    Even
    2.20
    There
    2.13
    Though
    2.11
    there
    2.08
    𝗦
    2.08
    Despite
    2.06
    ⡯
    2.03
    鏵
    2.03
    Activations Density 0.015%

    No Known Activations