© 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. 92997
    Prev
    Next
    INDEX
    Explanations

    Statement, privacy, control

    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
    んですが
    0.49
    ֹ
    0.46
    )?
    0.42
    িনের
    0.42
    )!
    0.41
    亏
    0.41
     방정식
    0.41
    を用いる
    0.40
     ፍ
    0.40
    埶
    0.40
    POSITIVE LOGITS
    sid
    0.49
    حد
    0.47
    geojson
    0.47
    future
    0.46
    سط
    0.44
    ፴
    0.44
    endis
    0.43
    кугӀ
    0.43
    باز
    0.42
     soybeans
    0.42
    Activations Density 0.000%

    No Known Activations