© 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. 34-GEMMASCOPE-RES-131K
    4. 118910
    Prev
    Next
    INDEX
    Explanations

    actually

    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
     IMO
    -1.23
     IMHO
    -1.23
     imo
    -1.23
     tersebut
    -1.20
    だって
    -1.17
    idorm
    -1.16
     as
    -1.13
     these
    -1.11
    多次
    -1.11
     reportedly
    -1.09
    POSITIVE LOGITS
    actually
    2.11
     actually
    2.09
    really
    1.72
    pretty
    1.61
     basically
    1.59
     eigenlijk
    1.59
     pretty
    1.56
     faktisk
    1.53
    basically
    1.53
    Actually
    1.52
    Activations Density 0.033%

    No Known Activations