© 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. 188142
    Prev
    Next
    INDEX
    Explanations

    access, questions, states

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

    daily, hourly, or monthly plans

    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
     వర
    0.44
    冲
    0.43
    래
    0.43
    却
    0.42
    য
    0.41
    క్తి
    0.41
    itance
    0.41
    getContentPane
    0.40
    iterator
    0.39
     ";
    0.39
    POSITIVE LOGITS
     acceso
    0.57
     presos
    0.57
     anx
    0.56
     questione
    0.55
     accesso
    0.55
     esclav
    0.55
     osobe
    0.54
     indicato
    0.54
     plazo
    0.53
     memberi
    0.53
    Activations Density 0.001%

    No Known Activations