© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3433
    Prev
    Next
    INDEX
    Explanations

    combinations and flow

    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
     relativamente
    0.44
    ។
    0.44
     neurotic
    0.44
    achron
    0.43
     otherworldly
    0.42
    ）」
    0.42
     idiosyncratic
    0.42
    。」
    0.41
     प्रयत्न
    0.41
     sadistic
    0.41
    POSITIVE LOGITS
     galore
    0.38
     Plantation
    0.35
     cafe
    0.34
     with
    0.34
     Gardens
    0.33
    5
    0.32
     parks
    0.32
    6
    0.32
     নদীর
    0.32
     barber
    0.32
    Activations Density 0.364%

    No Known Activations