© 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. 237533
    Prev
    Next
    INDEX
    Explanations

    certain verbs followed by specific nouns

    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
    <unused54>
    0.55
     ትንሽ
    0.49
     ನೆ
    0.49
    <unused67>
    0.48
     መን
    0.48
     déplacement
    0.46
     ሞ
    0.46
    persons
    0.46
     ሁ
    0.45
     すご
    0.45
    POSITIVE LOGITS
     dependen
    0.45
    \
    0.44
     exhibited
    0.44
    כ
    0.43
     simplified
    0.42
     mape
    0.41
     Infantil
    0.41
     explanatory
    0.40
    vast
    0.40
    ensional
    0.39
    Activations Density 0.001%

    No Known Activations