© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    introducing explanations or descriptions

    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
    ag
    0.48
    pt
    0.47
     xhrObj
    0.46
    ib
    0.43
    grad
    0.42
    break
    0.41
    },
    0.41
    agar
    0.41
    rios
    0.40
    Í
    0.40
    POSITIVE LOGITS
    міна
    0.49
    Utilities
    0.45
    邺
    0.44
    да
    0.44
    ޤ
    0.44
     possibilità
    0.44
    ཌ
    0.44
    цію
    0.43
     coût
    0.43
    Doesn
    0.42
    Activations Density 0.005%

    No Known Activations