© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8276
    Prev
    Next
    INDEX
    Explanations

    signals travelling

    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_16_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
    :
    0.70
    8
    0.60
    7
    0.59
    ERRY
    0.55
    6
    0.55
    *)
    0.52
    bits
    0.50
    >
    0.50
    Jeśli
    0.49
    9
    0.48
    POSITIVE LOGITS
     be
    0.47
     bloque
    0.46
     trabajar
    0.45
     ſt
    0.45
     deja
    0.45
     liner
    0.44
    ين
    0.44
     colaborar
    0.44
     una
    0.44
     resemblance
    0.43
    Activations Density 0.001%

    No Known Activations