© 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. 187895
    Prev
    Next
    INDEX
    Explanations

    Arianators and Beliebers

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

    impact performance, cracking, consensual

    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
    max
    0.52
    hi
    0.44
    га
    0.44
    čen
    0.43
    za
    0.43
    oids
    0.42
    默默
    0.42
    杆
    0.42
    otransferase
    0.41
    后
    0.41
    POSITIVE LOGITS
     bús
    0.57
     mastect
    0.56
     노래
    0.55
     accidens
    0.54
     defam
    0.53
     osoby
    0.52
     trauer
    0.52
     супра
    0.52
    ാരി
    0.51
     auffi
    0.51
    Activations Density 0.000%

    No Known Activations