© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90693
    Prev
    Next
    INDEX
    Explanations

    trapped, capture, detective

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

    foreign language content

    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
     manifestation
    0.44
     भव
    0.44
    委
    0.44
     vett
    0.43
    々な
    0.42
    LZ
    0.42
    據
    0.42
    τυχ
    0.41
    象
    0.41
    arriv
    0.41
    POSITIVE LOGITS
    ेच्छा
    0.45
    োঁ
    0.41
    لي
    0.41
    ler
    0.40
    िं
    0.40
     ∀
    0.40
     échanc
    0.40
    দাম
    0.39
    для
    0.38
     independiente
    0.38
    Activations Density 0.001%

    No Known Activations