© 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. 107284
    Prev
    Next
    INDEX
    Explanations

    made to donations

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

    verbs followed by prepositions

    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
     antice
    0.47
    รือ
    0.46
    𝙖
    0.46
     прось
    0.45
     lasciato
    0.44
     შეიძლება
    0.42
     大き
    0.42
     እንቅ
    0.42
    suggestions
    0.42
    イレ
    0.41
    POSITIVE LOGITS
     kepada
    0.50
     in
    0.44
     f
    0.43
     on
    0.43
     h
    0.42
     tycoon
    0.42
     u
    0.41
     for
    0.41
    对自己
    0.41
     tyrant
    0.40
    Activations Density 0.002%

    No Known Activations