© 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. 196506
    Prev
    Next
    INDEX
    Explanations

    Porter, denied, offense, them

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

    specific, trending, consistently, common, functional, sensible

    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
    lessly
    0.48
     beautifully
    0.45
    phase
    0.41
     telescopes
    0.41
     কমিয়ে
    0.40
     falsely
    0.40
     densities
    0.39
    絶
    0.39
    onic
    0.39
     bacteria
    0.39
    POSITIVE LOGITS
     તેમના
    0.46
    స
    0.42
    வி
    0.41
    깐
    0.41
    देश
    0.41
    कला
    0.41
    踩
    0.41
    कार
    0.40
    AuthConfig
    0.40
    গত
    0.40
    Activations Density 0.000%

    No Known Activations