© 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. 780
    Prev
    Next
    INDEX
    Explanations

    promoting sustainability and energy

    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
    ൮
    0.38
    Scorch
    0.36
     nutzen
    0.36
    ڡ
    0.34
    Khokhlov
    0.34
     realizó
    0.34
     hilfreich
    0.33
    த்தினை
    0.33
    𒀸
    0.33
    folg
    0.33
    POSITIVE LOGITS
     各
    0.30
      
    0.30
     don
    0.30
     fal
    0.29
    ARD
    0.28
     第
    0.28
     黒
    0.28
     Mother
    0.28
     tales
    0.28
     ღ
    0.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.