© 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. 86036
    Prev
    Next
    INDEX
    Explanations

    noun followed by verb/preposition

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

    phrases or clauses following certain tokens

    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
     P
    0.42
     write
    0.42
     transference
    0.42
    さんに
    0.41
     public
    0.39
     world
    0.38
    使う
    0.37
     outsiders
    0.37
     사회
    0.37
     journalism
    0.36
    POSITIVE LOGITS
     effectués
    0.44
    쨌
    0.43
     поздрав
    0.42
     herein
    0.41
    ٥
    0.41
     hilfre
    0.40
     этих
    0.40
     thereof
    0.40
    surprisingly
    0.40
    न्होंने
    0.39
    Activations Density 0.004%

    No Known Activations