© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37750
    Prev
    Next
    INDEX
    Explanations

    search, read, detect, formal

    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
     a
    0.75
     to
    0.57
     reple
    0.50
    ént
    0.50
    ina
    0.50
    }$=
    0.47
    ă
    0.47
     rozpoczę
    0.45
     aptly
    0.45
     trochu
    0.44
    POSITIVE LOGITS
    dır
    0.66
    u
    0.64
    스의
    0.59
    သောအ
    0.58
    스
    0.56
    のス
    0.55
    sst
    0.49
     przedsiębior
    0.49
    gares
    0.49
    ປ
    0.49
    Activations Density 0.013%

    No Known Activations