Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 141
    Prev
    Next
    INDEX
    Explanations

    requesting more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    ].
    0.56
     anderem
    0.56
    !
    0.51
    Jadi
    0.50
    -.
    0.50
     البته
    0.50
    Kalau
    0.49
     appunto
    0.49
    Selain
    0.48
    .}
    0.48
    POSITIVE LOGITS
     there
    1.17
     it
    1.01
     we
    0.99
     they
    0.93
     you
    0.89
     consider
    0.89
    there
    0.85
     hãy
    0.81
     chances
    0.73
     theres
    0.71
    Activations Density 0.255%

    No Known Activations