© 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. 60179
    Prev
    Next
    INDEX
    Explanations

    entity, slaves, neighborhood, advisors

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

    mathematical functions and algorithms

    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
     ಮಾತನಾಡ
    0.43
     Nitrate
    0.42
    㞔
    0.41
    遗憾
    0.41
    শুধু
    0.41
    ాల్సిన
    0.41
    年份
    0.40
     Fluorescence
    0.39
     Hydrochloride
    0.39
     FURTHER
    0.39
    POSITIVE LOGITS
     determina
    0.46
    tenth
    0.44
     ፈ
    0.43
     invariants
    0.43
    hebung
    0.42
     determinar
    0.42
    enk
    0.41
     abat
    0.40
     algorit
    0.40
     equation
    0.40
    Activations Density 0.000%

    No Known Activations