© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31167
    Prev
    Next
    INDEX
    Explanations

    write memory, involuntary contractions, key

    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_40_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
    志森
    0.46
    お店
    0.40
    inspection
    0.39
    電動
    0.39
    UTONIUM
    0.38
    高温
    0.38
    chanted
    0.38
    姆
    0.38
    店舗
    0.38
     पस
    0.37
    POSITIVE LOGITS
     line
    0.44
     Hash
    0.43
     Wait
    0.42
     â
    0.41
     Waiting
    0.40
    线
    0.40
    Mâ
    0.38
     waiting
    0.38
    ári
    0.38
     hash
    0.38
    Activations Density 0.000%

    No Known Activations