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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208514
    Prev
    Next
    INDEX
    Explanations

    without notice or hand

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

    budget management, massive amounts, influenced by, social importance

    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_31_width_262k_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
    ascular
    0.42
     neglect
    0.41
    failed
    0.40
    ナトリウム
    0.40
    flop
    0.40
    ウム
    0.39
    African
    0.39
    ほ
    0.38
    econom
    0.38
    dba
    0.38
    POSITIVE LOGITS
     đoạn
    0.55
     segmento
    0.50
    မြို့
    0.50
     inşa
    0.50
     虽然
    0.48
     Lyft
    0.48
    াপতি
    0.48
    铐
    0.48
     nổi
    0.46
     einzigen
    0.46
    Activations Density 0.000%

    No Known Activations