© 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. 137687
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    describing states or arrangements

    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
    <start_of_image>
    0.42
     Xem
    0.41
    滹
    0.41
     అనేది
    0.40
     B
    0.40
     FSB
    0.40
    ىر
    0.40
    點
    0.40
     Phenomen
    0.39
     হাদী
    0.39
    POSITIVE LOGITS
    abhavam
    0.51
    trav
    0.47
    नए
    0.47
     travellers
    0.46
    onSubmit
    0.45
     rappelle
    0.44
     abusing
    0.44
    枢
    0.44
     choć
    0.43
     nhớ
    0.43
    Activations Density 0.000%

    No Known Activations