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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 17344
    Prev
    Next
    INDEX
    Explanations

    waters and islands off

    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
    亢
    0.45
    窰
    0.44
    山上
    0.44
    ையைப்
    0.42
     cvec
    0.42
    蘚
    0.42
    鳟
    0.41
    蟋
    0.40
    AudioAsset
    0.39
     ንጥረ
    0.39
    POSITIVE LOGITS
     off
    1.99
    off
    1.49
     offshore
    1.41
     Off
    1.34
    Off
    1.33
     OFF
    1.21
     Offshore
    1.09
     offs
    1.07
    オフ
    1.06
    offs
    1.00
    Activations Density 0.013%

    No Known Activations