© 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. 200473
    Prev
    Next
    INDEX
    Explanations

    sensitive matters and difficulties

    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
     assis
    0.46
     accept
    0.46
     saluran
    0.44
     accep
    0.43
    බන්ධ
    0.43
     Safegu
    0.40
    护
    0.40
     strengthen
    0.40
     sims
    0.40
     suppress
    0.39
    POSITIVE LOGITS
    ተር
    0.46
    iko
    0.45
     estratégia
    0.44
    ADER
    0.44
    ený
    0.43
    ռ
    0.43
    ber
    0.42
    transformer
    0.42
    يك
    0.42
    Droite
    0.41
    Activations Density 0.006%

    No Known Activations