© 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. 31-GEMMASCOPE-2-RES-65K
    7. 11030
    Prev
    Next
    INDEX
    Explanations

    mini-split systems

    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_65k_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
     zodat
    0.42
    olič
    0.41
     vutto
    0.40
    amazing
    0.40
    漃
    0.40
    Amazing
    0.39
     patitth
    0.39
    grandfather
    0.39
    ینہ
    0.39
     sabbam
    0.39
    POSITIVE LOGITS
    iejsc
    0.41
     Deniz
    0.39
     cosmetic
    0.38
     pictureBox
    0.38
     cutaneous
    0.38
    ╁
    0.38
     tileSize
    0.37
     psychiatric
    0.37
     Lep
    0.36
     அவை
    0.36
    Activations Density 0.003%

    No Known Activations