© 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. 197916
    Prev
    Next
    INDEX
    Explanations

    your requirements

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

    Queen Elizabeth

    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
    땠
    0.48
    เง
    0.46
    萛
    0.45
     புராண
    0.45
    ༨
    0.45
    ๘
    0.45
     акысыз
    0.44
    电气
    0.44
    맣
    0.43
    大多
    0.43
    POSITIVE LOGITS
    af
    0.58
    id
    0.49
     la
    0.48
    uk
    0.46
    elis
    0.46
    odz
    0.46
    of
    0.45
     swab
    0.45
    adf
    0.44
    ap
    0.44
    Activations Density 0.000%

    No Known Activations