© 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. 151175
    Prev
    Next
    INDEX
    Explanations

    report, decide, attract, projects, experiment

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

    connecting conjunctions and descriptive follow-ups

    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
    ה
    0.52
    മായ
    0.50
    لم
    0.50
    </html>
    0.48
    по
    0.48
    ча
    0.48
    COMMON
    0.48
    expanded
    0.46
    ت
    0.46
    ра
    0.46
    POSITIVE LOGITS
     nul
    0.51
     vårt
    0.49
     proximal
    0.47
     Outs
    0.47
     suppos
    0.46
     aktuell
    0.46
     शेवट
    0.45
     outsourcing
    0.44
     läk
    0.44
     narcot
    0.44
    Activations Density 0.000%

    No Known Activations