© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45402
    Prev
    Next
    INDEX
    Explanations

    domains, accounts, successfully, easily digested

    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_31_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
    эл
    0.55
    俔
    0.53
     бал
    0.51
    happy
    0.50
    쳥
    0.50
     natthi
    0.49
    drugs
    0.48
    栃
    0.47
     счёт
    0.46
    ли
    0.46
    POSITIVE LOGITS
     Datas
    0.53
     became
    0.47
     Neon
    0.46
     from
    0.45
     datasheet
    0.45
    ophenone
    0.44
     Federation
    0.44
     Dj
    0.44
     George
    0.43
     that
    0.43
    Activations Density 0.000%

    No Known Activations