© 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. 138813
    Prev
    Next
    INDEX
    Explanations

    AI development and scientific concepts

    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
     projection
    0.52
     методи
    0.47
     retreated
    0.47
     microseconds
    0.46
     suicide
    0.46
    >≥</
    0.46
     strangled
    0.46
     leakage
    0.45
     curve
    0.45
     shielded
    0.45
    POSITIVE LOGITS
     هذا
    0.53
    این
    0.50
     twor
    0.49
     Dieser
    0.48
    为人
    0.47
     Tiny
    0.46
     nowy
    0.45
    Stop
    0.45
     आईआई
    0.44
    罗
    0.44
    Activations Density 0.001%

    No Known Activations