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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 118594
    Prev
    Next
    INDEX
    Explanations

    journey takes time

    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
    ಣಿ
    0.48
     આવ
    0.48
    કો
    0.48
    ції
    0.48
    ᾗ
    0.47
    હિતી
    0.46
    }^{-},
    0.46
    ुभ
    0.46
    厩
    0.46
     پائی
    0.46
    POSITIVE LOGITS
    of
    0.60
     popsicle
    0.59
    0.58
                     
    0.51
    ।
    0.51
    are
    0.50
     of
    0.49
     courtroom
    0.48
     le
    0.47
     temperature
    0.47
    Activations Density 0.006%

    No Known Activations