© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8330
    Prev
    Next
    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    ABLES
    0.64
     നമഃ
    0.61
    ICAN
    0.60
    চৈতন্য
    0.60
    Ⴖ
    0.60
    உ
    0.59
     Crystallogr
    0.58
    춧
    0.58
    Glu
    0.58
    preconnect
    0.57
    POSITIVE LOGITS
     each
    0.74
    各自
    0.70
     "
    0.69
     Each
    0.69
     vulnerability
    0.68
     commentary
    0.66
     jeweils
    0.64
     either
    0.63
     vulnerable
    0.62
     whether
    0.62
    Activations Density 0.005%

    No Known Activations