© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    numbers, mathematical operations, and list items

    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
     it
    -1.35
     there
    -1.19
     hini
    -1.18
    <bos>
    -1.13
    ፉ
    -1.07
    вня
    -1.06
     although
    -1.04
     alfabeto
    -1.02
     همچنین
    -1.02
     also
    -1.02
    POSITIVE LOGITS
     günstiger
    1.16
    crição
    1.16
     the
    1.14
     Sigh
    1.13
     zweimal
    1.12
     zewnętrzne
    1.11
    的問題
    1.11
    ?
    1.10
    ologue
    1.05
     entwickelte
    1.03
    Activations Density 0.015%

    No Known Activations