© 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. 241438
    Prev
    Next
    INDEX
    Explanations

    actions followed by prepositions or descriptors

    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
     collapses
    0.52
    트
    0.50
    ;++
    0.49
     ở
    0.49
    yt
    0.49
     operates
    0.49
     typh
    0.49
     avg
    0.48
     inscrito
    0.48
     tổ
    0.48
    POSITIVE LOGITS
    ANDO
    0.47
     அமைச்சர்
    0.45
    Eric
    0.45
    KING
    0.44
    BILL
    0.44
    МІ
    0.43
    UM
    0.42
    讓
    0.41
    䙷
    0.41
    耀
    0.41
    Activations Density 0.000%

    No Known Activations