© 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. 73105
    Prev
    Next
    INDEX
    Explanations

    financial and organizational structures

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

    hypothetical scenarios and conditional statements

    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
     vuccati
    0.46
     нази
    0.46
     drows
    0.43
     apportion
    0.42
     meditating
    0.42
     regioni
    0.42
     portraying
    0.41
    諾
    0.41
     இடங்களில்
    0.41
     erecting
    0.40
    POSITIVE LOGITS
    yfik
    0.56
     amélior
    0.46
    டி
    0.46
     Improved
    0.46
     améli
    0.45
    辍
    0.44
     Perf
    0.43
     Power
    0.43
     improved
    0.43
     Toxicity
    0.42
    Activations Density 0.000%

    No Known Activations