© 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. 41711
    Prev
    Next
    INDEX
    Explanations

    cultural and engineering 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
    }^{\
    0.44
    ari
    0.44
     ૧
    0.43
     Zusätzlich
    0.43
    unately
    0.43
     "?
    0.43
    ipped
    0.42
     wird
    0.41
     выполняется
    0.41
    p
    0.40
    POSITIVE LOGITS
    खड़
    0.51
     dumping
    0.46
     Commission
    0.45
     siting
    0.45
     faculty
    0.45
     Steelers
    0.45
     barring
    0.44
    ᱢ
    0.44
    γου
    0.43
     commissioning
    0.42
    Activations Density 0.001%

    No Known Activations