© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

    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_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
    া
    0.42
     of
    0.41
    銚
    0.38
    '
    0.38
    ,
    0.37
    )
    0.36
    ıp
    0.36
    이지만
    0.36
     অথবা
    0.36
    者
    0.35
    POSITIVE LOGITS
     ஆகிய
    0.51
     എന്നീ
    0.50
     ஆகியவை
    0.48
     आलोक
    0.46
     यामुळे
    0.43
     എന്നിവ
    0.43
     മറ്റ്
    0.42
     ஆகியோர்
    0.42
     oraz
    0.42
     साहस
    0.42
    Activations Density 0.311%

    No Known Activations