© 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. 11425
    Prev
    Next
    INDEX
    Explanations

    actions and states

    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
    เนื้อ
    -0.94
    𝘚
    -0.93
     actualmente
    -0.88
    sterna
    -0.85
     currently
    -0.84
     disques
    -0.84
     goûts
    -0.83
    rô
    -0.83
     de
    -0.83
     clung
    -0.82
    POSITIVE LOGITS
    ning
    1.09
     разнообраз
    1.02
    σου
    0.99
    })();
    0.96
    rawdź
    0.94
     każdej
    0.94
     corrupción
    0.93
    fillment
    0.92
     públicos
    0.92
    rester
    0.90
    Activations Density 0.084%

    No Known Activations