© 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. 216734
    Prev
    Next
    INDEX
    Explanations

    my own

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

    this is

    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
    annte
    0.47
    erde
    0.46
    utel
    0.46
    öffent
    0.45
    害怕
    0.43
     प्रतिष्ठित
    0.43
    incer
    0.42
    曏
    0.42
    aku
    0.42
     ভী
    0.42
    POSITIVE LOGITS
     actúa
    0.46
     exerts
    0.46
     povas
    0.46
     exista
    0.46
     primarily
    0.45
     anchors
    0.45
     imbalances
    0.45
     payloads
    0.45
     kaleidoscopic
    0.44
     menand
    0.43
    Activations Density 0.000%

    No Known Activations