© 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. 12152
    Prev
    Next
    INDEX
    Explanations

    first album or release

    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
     when
    -1.59
     quickly
    -1.21
     various
    -1.13
     through
    -1.05
    各種
    -1.03
     could
    -1.03
     and
    -1.02
     When
    -1.02
     during
    -0.98
    When
    -0.98
    POSITIVE LOGITS
     памя
    1.32
     tercio
    1.15
     fewer
    1.13
     két
    1.13
     usamos
    1.08
     thème
    1.08
    requipa
    1.07
     pesar
    1.06
     prénom
    1.06
     wieder
    1.05
    Activations Density 0.087%

    No Known Activations