© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5124
    Prev
    Next
    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite

    structured query language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }"]
    0.42
     sentimiento
    0.39
    逓
    0.38
    "]]
    0.38
    年来
    0.38
    জর
    0.38
    }];
    0.37
     derogatory
    0.37
     phổ
    0.36
    ']}
    0.36
    POSITIVE LOGITS
    guided
    0.38
     mundur
    0.38
     guided
    0.38
    mund
    0.38
     préd
    0.38
     Tij
    0.38
    spaced
    0.37
     çal
    0.37
    intera
    0.36
    obucket
    0.36
    Activations Density 0.000%

    No Known Activations