© 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. 64871
    Prev
    Next
    INDEX
    Explanations

    and followed by verbs

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

    community discussions

    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
     Comics
    0.51
     スマ
    0.50
     Anyone
    0.50
     थक
    0.50
     Νο
    0.48
     床
    0.47
     Hitler
    0.46
     лига
    0.45
    infty
    0.45
     Tuchel
    0.45
    POSITIVE LOGITS
     pembuatan
    0.49
     exuberant
    0.44
    েরা
    0.41
     sejahtera
    0.41
     specifications
    0.39
     additions
    0.39
     தாண்ட
    0.39
    ocre
    0.38
    })-\
    0.38
    IEN
    0.38
    Activations Density 0.000%

    No Known Activations