© 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. 69377
    Prev
    Next
    INDEX
    Explanations

    titles of specific places and media

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

    `Terror` activity, `record` is, marshmallows

    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
    דרך
    0.33
    ױ
    0.30
    שת
    0.30
    תי
    0.30
    מו
    0.29
    ותר
    0.29
    ד
    0.29
    ّ
    0.29
    צ
    0.29
    צה
    0.28
    POSITIVE LOGITS
     aforementioned
    0.30
     muttered
    0.26
     mischievous
    0.25
     erster
    0.25
     avoid
    0.25
     ആദ്യ
    0.25
     inclement
    0.25
     SAW
    0.24
     echoing
    0.24
     Định
    0.24
    Activations Density 0.312%

    No Known Activations