© 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. 53-GEMMASCOPE-2-RES-262K
    7. 14591
    Prev
    Next
    INDEX
    Explanations

    innocent, innocence, or harmlessness

    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_53_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
     verpflicht
    0.40
    枌
    0.38
    फलता
    0.37
     Flexible
    0.37
     fab
    0.36
     etik
    0.36
    砣
    0.35
    hesive
    0.35
     облі
    0.35
    黯
    0.35
    POSITIVE LOGITS
     innocent
    3.98
     innocence
    3.72
     innoc
    3.58
     Innocent
    3.38
     Innoc
    3.33
     inoc
    2.94
     innocuous
    2.27
    inn
    2.23
     harmless
    2.11
     inoculation
    2.00
    Activations Density 0.040%

    No Known Activations