© 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. 108536
    Prev
    Next
    INDEX
    Explanations

    security, systems, computer, TPM

    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
     BBC
    0.44
    Y
    0.42
     murderous
    0.42
     darkness
    0.40
     rebellious
    0.40
    right
    0.40
    IGN
    0.40
     brightness
    0.40
     mob
    0.40
    Z
    0.39
    POSITIVE LOGITS
    PropertyParam
    0.47
    㿟
    0.45
     расходов
    0.44
    泍
    0.44
    тар
    0.44
    ンダント
    0.44
    툐
    0.44
    苖
    0.43
    ບບ
    0.43
    سترول
    0.43
    Activations Density 0.005%

    No Known Activations