© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4295
    Prev
    Next
    INDEX
    Explanations

    graphic or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     digamos
    0.19
     δύο
    0.19
    분의
    0.19
    \%,
    0.19
    Ბ
    0.18
    Გ
    0.18
    合計
    0.18
    靝
    0.18
     belirli
    0.18
     বেশকিছু
    0.18
    POSITIVE LOGITS
     is
    0.22
    ches
    0.20
    ígenes
    0.18
    rente
    0.18
     has
    0.17
    ِ
    0.17
     prevents
    0.17
    vis
    0.17
    ofacial
    0.17
    ↵
    0.16
    Activations Density 0.371%

    No Known Activations