© 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-65K
    7. 64622
    Prev
    Next
    INDEX
    Explanations

    masking and threats

    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_65k_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
    so
    0.42
     hydroly
    0.41
     lactation
    0.39
    rai
    0.39
    dib
    0.38
     પણ
    0.38
    ickej
    0.38
    也
    0.38
    unction
    0.38
     cofactor
    0.38
    POSITIVE LOGITS
    にくい
    0.50
    শিদ
    0.47
     ambao
    0.47
     वेरिए
    0.46
    हरू
    0.45
     MIA
    0.45
     инде
    0.44
     صارفین
    0.44
    შირ
    0.43
     tilbage
    0.43
    Activations Density 0.001%

    No Known Activations