© 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. 31838
    Prev
    Next
    INDEX
    Explanations

    anyhow obsolete

    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
     freezing
    0.62
    أ
    0.58
    ೋಜನ
    0.55
     reversion
    0.54
     legalization
    0.53
     ideology
    0.51
     overpowered
    0.50
    ーター
    0.49
     swelling
    0.49
    م
    0.48
    POSITIVE LOGITS
    pc
    0.68
     ພວກເຮົາ
    0.68
    paper
    0.65
    cases
    0.64
    mid
    0.63
    bie
    0.62
    ва
    0.61
     certamente
    0.61
    𝕡
    0.61
    ológica
    0.61
    Activations Density 0.000%

    No Known Activations