© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12337
    Prev
    Next
    INDEX
    Explanations

    loading scripts and styles

    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
    -1.15
     with
    -1.12
     using
    -1.10
     averiguar
    -1.09
     decision
    -1.06
     length
    -1.06
     cells
    -1.03
     his
    -1.03
     ability
    -1.02
     family
    -1.02
    POSITIVE LOGITS
    もちゃ
    1.20
     пирог
    1.15
     invariable
    1.09
    quellen
    1.07
     periodicals
    1.07
    ﻹ
    1.04
    𝒙
    1.01
     شدن
    1.00
    revealed
    1.00
    Studying
    1.00
    Activations Density 0.036%

    No Known Activations