© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    PII, P-codes, organizations, tech frameworks

    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
    ponenten
    0.40
    𝙉
    0.40
    න්
    0.39
    ্লাস
    0.38
    ﺩ
    0.37
    鋐
    0.37
     gjennom
    0.36
    kontakt
    0.36
     Menschen
    0.36
    "')
    0.36
    POSITIVE LOGITS
     reorganization
    0.47
     preoccupation
    0.44
     PZ
    0.42
     politics
    0.42
     punches
    0.41
     P
    0.40
     fights
    0.40
     p
    0.40
     interface
    0.40
     PSO
    0.40
    Activations Density 0.244%

    No Known Activations