© 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. 149307
    Prev
    Next
    INDEX
    Explanations

    regular updates, signed, any surplus

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

    for educational purposes

    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
     திர
    0.50
     equil
    0.44
     vivir
    0.44
     noemen
    0.44
     continua
    0.43
    
    0.43
     عين
    0.43
     நியூ
    0.42
     marginal
    0.42
     www
    0.41
    POSITIVE LOGITS
    h
    0.46
     Attorneys
    0.46
    ameni
    0.45
     অপরিচিত
    0.45
    рі
    0.43
    ]。
    0.43
    hunt
    0.42
    adar
    0.42
    었습니다
    0.41
    t
    0.41
    Activations Density 0.007%

    No Known Activations