© 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. 168789
    Prev
    Next
    INDEX
    Explanations

    complex or specific details

    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
     skyscraper
    0.45
    ".*:
    0.45
     chargingStation
    0.44
     evaluator
    0.43
    υγ
    0.43
     sintering
    0.43
    彊
    0.43
     condominium
    0.42
     providing
    0.42
    ystring
    0.42
    POSITIVE LOGITS
    Symptoms
    0.46
    didn
    0.45
    Ctrl
    0.45
    Explain
    0.43
     அவரின்
    0.43
    g
    0.43
    อาการ
    0.43
     ihnen
    0.42
    Expand
    0.42
     симпто
    0.42
    Activations Density 0.004%

    No Known Activations