© 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. 169421
    Prev
    Next
    INDEX
    Explanations

    places and states

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

    constructively or destructively

    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
     ການ
    0.49
     बदलाव
    0.47
    ４
    0.46
    蛆
    0.45
    inci
    0.45
    ilerini
    0.45
    移动
    0.44
    燚
    0.44
    淔
    0.44
     infatti
    0.44
    POSITIVE LOGITS
     powerhouse
    0.54
     aesthetic
    0.48
     neurotrans
    0.46
     physiological
    0.45
     euph
    0.44
     podcast
    0.43
     vague
    0.41
     toned
    0.41
    aesthetic
    0.41
     bioge
    0.40
    Activations Density 0.000%

    No Known Activations