© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    technical and common phrases

    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
     infringed
    0.56
    BlockUsed
    0.56
    dyž
    0.54
    ᱐
    0.53
    স্থানীয়
    0.52
    Pokud
    0.52
    InstanceOf
    0.51
    वर्क
    0.50
    ్యాచ్
    0.50
    innings
    0.49
    POSITIVE LOGITS
    _
    0.59
    the
    0.57
    this
    0.55
    it
    0.53
    u
    0.52
    𝓮
    0.50
     nuclé
    0.49
     pesso
    0.49
     бе
    0.49
     otra
    0.49
    Activations Density 0.002%

    No Known Activations