© 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. 11568
    Prev
    Next
    INDEX
    Explanations

    highs, lows, and prices

    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
    })
    -1.28
     children
    -1.27
    Život
    -1.26
     OGSÅ
    -1.22
    nung
    -1.20
    Jäh
    -1.13
    stateProvider
    -1.13
    \},
    -1.12
    setViewName
    -1.11
    SON
    -1.10
    POSITIVE LOGITS
     today
    1.38
    がありますが
    1.23
     arbetar
    1.11
     πρ
    1.09
    UNIFIED
    1.09
     yesterday
    1.09
    фотография
    1.09
     earliest
    1.09
     utveckling
    1.09
     informou
    1.07
    Activations Density 0.005%

    No Known Activations