© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119026
    Prev
    Next
    INDEX
    Explanations

    tisanes, tissular

    np_acts-logits-general · gemini-2.5-flash-lite

    words or prefixes that resemble 'tis' such as 'tisane', 'tissue', or names with 'Tis' like 'Etisalat'.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Neues
    -0.76
    кина
    -0.75
    jane
    -0.73
    体は
    -0.73
     prossimo
    -0.69
    AUSTRALIA
    -0.68
    ☀
    -0.67
     conductance
    -0.66
    горь
    -0.66
    tey
    -0.66
    POSITIVE LOGITS
    ular
    0.82
    idigung
    0.75
    nosis
    0.71
     pools
    0.70
    ilar
    0.70
    提出了
    0.70
    dale
    0.69
    araf
    0.68
    EMENTS
    0.68
     capable
    0.67
    Activations Density 0.032%

    No Known Activations