© 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. 31-GEMMASCOPE-2-RES-262K
    7. 7180
    Prev
    Next
    INDEX
    Explanations

    undeciphered scripts or states

    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_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
    ruitment
    0.47
    oint
    0.45
    Support
    0.41
    parency
    0.41
    وروب
    0.41
     最后
    0.41
    利
    0.41
    Attrib
    0.40
    }}/
    0.40
     mandib
    0.40
    POSITIVE LOGITS
     disse
    0.48
     reins
    0.42
     doskona
    0.42
     mercur
    0.41
     Gil
    0.41
     sprink
    0.41
     excellent
    0.41
     Thomas
    0.40
     declara
    0.39
     Dutton
    0.39
    Activations Density 0.000%

    No Known Activations