© 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. 28540
    Prev
    Next
    INDEX
    Explanations

    multiply, destroy, remember, languages

    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
    atorial
    0.50
     real
    0.44
    অল
    0.44
     daytime
    0.43
    ார்
    0.40
    ოტ
    0.40
    酸
    0.39
     assumption
    0.39
    仟
    0.39
    ajero
    0.39
    POSITIVE LOGITS
     লিখে
    0.45
     dirigés
    0.43
     سمت
    0.43
     Haga
    0.43
     Udemy
    0.43
     اض
    0.43
    ȩ
    0.43
     مما
    0.42
    骖
    0.42
     számos
    0.41
    Activations Density 0.004%

    No Known Activations