© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136162
    Prev
    Next
    INDEX
    Explanations

    earthen gleam, subsoil gold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ੧
    0.46
     cò
    0.43
    ksjon
    0.43
    𝟎
    0.42
     dû
    0.41
     常
    0.40
    ūra
    0.40
    рата
    0.39
     vutt
    0.38
    .-(
    0.38
    POSITIVE LOGITS
     toiletries
    0.42
    _{{\
    0.42
     சைவ
    0.40
     loyalty
    0.40
     biographies
    0.38
     gus
    0.35
     hostages
    0.35
     Loyalty
    0.35
    DATAS
    0.35
    stays
    0.35
    Activations Density 0.000%

    No Known Activations