© 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. 85858
    Prev
    Next
    INDEX
    Explanations

    Saul Hudson, Kripke, ollies

    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
    hiddenMap
    0.62
    en
    0.58
    ة
    0.58
    ing
    0.57
    thisStudent
    0.57
     และ
    0.54
    ه
    0.53
    া
    0.51
    _
    0.51
    -:
    0.50
    POSITIVE LOGITS
     felic
    0.52
     outreach
    0.51
     मलेशिया
    0.51
    imes
    0.50
     диви
    0.50
     począ
    0.50
    ゼロ
    0.50
    Responding
    0.50
     irrevers
    0.50
     өл
    0.50
    Activations Density 0.000%

    No Known Activations