© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8135
    Prev
    Next
    INDEX
    Explanations

    assembly instructions and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asti
    0.52
    }=$
    0.50
    appoint
    0.50
    sensitive
    0.49
    bar
    0.48
    und
    0.48
    ences
    0.48
    gris
    0.48
    ampl
    0.47
    ।
    0.46
    POSITIVE LOGITS
     MODELS
    0.55
     DEVICE
    0.54
     segí
    0.51
     DEV
    0.50
    一
    0.48
     groupId
    0.48
    वणी
    0.47
     IDF
    0.47
    Ｍ
    0.46
     SERVER
    0.46
    Activations Density 0.000%

    No Known Activations