© 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. 124605
    Prev
    Next
    INDEX
    Explanations

    tons, pounds, kg, lb, hp, kw, rpm, g

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

    weights in tons or tonnes

    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
    𒁹
    0.53
     فٹ
    0.51
    選手
    0.50
    醎
    0.48
    arello
    0.48
    䂺
    0.46
    䔀
    0.44
    美國
    0.44
    輋
    0.44
     अराउंड
    0.43
    POSITIVE LOGITS
     brid
    0.46
     crim
    0.45
     s
    0.43
     jwt
    0.41
     erasure
    0.41
     aura
    0.41
    ↵
    0.41
     mating
    0.40
     boosts
    0.40
     r
    0.39
    Activations Density 0.000%

    No Known Activations