© 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. 90521
    Prev
    Next
    INDEX
    Explanations

    dispensary or voice

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

    asking for context

    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
     reproductive
    0.46
    ней
    0.46
     dispersal
    0.45
     interventions
    0.45
     vytvá
    0.44
    па
    0.44
     आंदोल
    0.44
    ौ
    0.44
     Reproductive
    0.43
     нега
    0.43
    POSITIVE LOGITS
    ra
    0.50
     Beispiel
    0.47
     Kür
    0.47
     Qatar
    0.46
     Kansas
    0.46
    沥
    0.45
    lo
    0.44
     Ksi
    0.44
     Baja
    0.44
     MINI
    0.43
    Activations Density 0.001%

    No Known Activations