© 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. 197283
    Prev
    Next
    INDEX
    Explanations

    player proposes, disk containing, produces, Merchant, its LIC

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

    creating, sending, or starting something

    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
     supplementary
    0.47
     neighbour
    0.45
     uncles
    0.44
     chees
    0.43
     discouraged
    0.43
     stun
    0.42
     aunts
    0.42
    要
    0.42
     neighbours
    0.41
     little
    0.41
    POSITIVE LOGITS
     अभिव
    0.56
    Ἠ
    0.52
    杢
    0.49
    URING
    0.48
    ूत
    0.46
     Roshelle
    0.46
    呓
    0.45
    ەم
    0.45
    गार
    0.45
     वीक
    0.44
    Activations Density 0.000%

    No Known Activations