© 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. 51087
    Prev
    Next
    INDEX
    Explanations

    malicious traffic

    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
     இழு
    0.51
    endaftaran
    0.50
    ruktur
    0.47
    䀒
    0.47
    VISIONS
    0.47
    რც
    0.46
    केशन
    0.46
    ᱖
    0.46
    ிகளும்
    0.46
    様々な
    0.45
    POSITIVE LOGITS
     warranty
    0.41
     Casey
    0.41
     assured
    0.41
     deemed
    0.39
     warranties
    0.38
     clientele
    0.38
     probleme
    0.38
     peaked
    0.37
     success
    0.37
     offensively
    0.37
    Activations Density 0.007%

    No Known Activations