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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130702
    Prev
    Next
    INDEX
    Explanations

    acting as, plays when, for the

    np_acts-logits-general · gemini-2.5-flash-lite

    reading social cues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ua
    0.57
    ot
    0.54
    up
    0.53
    uhan
    0.53
    oS
    0.52
     E
    0.51
     B
    0.50
     UNESCO
    0.46
    ip
    0.46
    ut
    0.46
    POSITIVE LOGITS
    ности
    0.55
     ayı
    0.50
    㥳
    0.49
    کار
    0.49
    میم
    0.48
     ay
    0.48
    隂
    0.47
     anggota
    0.47
    ௐ
    0.46
    मूर्ति
    0.46
    Activations Density 0.001%

    No Known Activations