© 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. 177539
    Prev
    Next
    INDEX
    Explanations

    signs of attention

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

    collider definitions

    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
     exaggerate
    0.46
     directories
    0.44
     depict
    0.44
     retained
    0.43
     asleep
    0.43
     отдельных
    0.42
    I
    0.42
     exagger
    0.42
     excav
    0.42
     filepath
    0.42
    POSITIVE LOGITS
    dv
    0.56
    labeled
    0.49
    customers
    0.49
    evident
    0.49
    ग्राह
    0.48
    (!$
    0.48
    fato
    0.48
    fis
    0.47
    iii
    0.47
    authent
    0.47
    Activations Density 0.001%

    No Known Activations