© 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. 125416
    Prev
    Next
    INDEX
    Explanations

    fit on, suit gorgeously, links these

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

    actions 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
    или
    0.52
     veya
    0.50
    શન
    0.47
    ್ರೆ
    0.46
    🌙
    0.46
    感じる
    0.45
    猙
    0.45
    ъ
    0.44
    vedi
    0.43
    älfte
    0.43
    POSITIVE LOGITS
     spectator
    0.43
     paradigms
    0.43
     constitutive
    0.42
    MODIFY
    0.42
     modalities
    0.42
     constrain
    0.41
     Topological
    0.41
     spectroscopic
    0.40
     spect
    0.40
     Ono
    0.40
    Activations Density 0.001%

    No Known Activations