© 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. 145432
    Prev
    Next
    INDEX
    Explanations

    discussing despised names

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

    breaking bad and prophets

    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
     Arrays
    0.44
     patted
    0.43
     neurop
    0.43
     conocidas
    0.42
     complexes
    0.40
    ∬
    0.39
    RIBUTION
    0.39
     propagating
    0.39
     biofilms
    0.39
     prevailed
    0.39
    POSITIVE LOGITS
    }$.)
    0.44
     그의
    0.41
    ḗ
    0.41
     ఒ
    0.41
    зяй
    0.41
     Pfer
    0.41
     Pří
    0.40
     کردہ
    0.40
    Ꭸ
    0.40
     அவருடைய
    0.39
    Activations Density 0.002%

    No Known Activations