© 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-65K
    7. 49136
    Prev
    Next
    INDEX
    Explanations

    links, development, cost

    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_65k_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
     Accounts
    0.43
     Hence
    0.39
     Honorary
    0.39
     Capt
    0.38
     ;
    0.38
     Throughout
    0.38
     Sacrament
    0.38
     Statistical
    0.37
     Accordingly
    0.37
     अकाउंट
    0.37
    POSITIVE LOGITS
     disparate
    0.49
     dichotom
    0.47
    ור
    0.47
     falling
    0.45
     plan
    0.44
     germinate
    0.43
     più
    0.42
     chem
    0.42
     bombe
    0.42
    ິ
    0.41
    Activations Density 0.000%

    No Known Activations