© 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. 17174
    Prev
    Next
    INDEX
    Explanations

    beyond generic or simple approaches

    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
     inasmuch
    0.55
     Incidentally
    0.55
    Incidentally
    0.54
    రువు
    0.48
    arquivo
    0.47
     immagine
    0.46
    REGIUNE
    0.46
    砝
    0.46
    ObjData
    0.46
    ﹉
    0.46
    POSITIVE LOGITS
     includes
    0.50
     including
    0.49
     applying
    0.48
     options
    0.47
     generic
    0.47
     included
    0.47
     Generic
    0.47
    3
    0.45
     style
    0.45
     use
    0.45
    Activations Density 0.034%

    No Known Activations