© 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. 32134
    Prev
    Next
    INDEX
    Explanations

    initial words in a phrase

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

    not settle

    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
    琛
    0.46
    Dictionaries
    0.45
    phthal
    0.44
    drm
    0.43
     catatan
    0.42
     चिह्न
    0.42
    ethical
    0.42
    wart
    0.40
    tta
    0.40
    TypeValue
    0.40
    POSITIVE LOGITS
     newcomer
    0.52
     ⚫
    0.50
     అనే
    0.49
     nói
    0.48
     postdoc
    0.46
    াইল
    0.45
     близ
    0.45
     spatially
    0.44
     আলোচ
    0.44
     occup
    0.44
    Activations Density 0.000%

    No Known Activations