© 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. 162555
    Prev
    Next
    INDEX
    Explanations

    being targeted

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

    abbreviations and specific contexts

    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
     ይህ
    0.50
     delightfully
    0.50
    Vậy
    0.47
    잭
    0.45
    ﭼ
    0.45
     自然
    0.44
     tastefully
    0.44
    ಳ್ಳ
    0.44
    닉
    0.44
     ২০১৩
    0.43
    POSITIVE LOGITS
     імені
    0.45
    lect
    0.45
    新的
    0.44
     fluv
    0.44
     imitating
    0.44
    engk
    0.43
     terb
    0.41
    antibodies
    0.41
     Menge
    0.41
    ʿ
    0.41
    Activations Density 0.000%

    No Known Activations