© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51256
    Prev
    Next
    INDEX
    Explanations

    riddle and ridge

    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_40_width_65k_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
    UNDS
    0.37
     이때
    0.36
    ><
    0.36
     dopo
    0.36
    anlagen
    0.36
     Wang
    0.35
     contaminate
    0.35
    uerra
    0.35
     garantiert
    0.35
     contamin
    0.35
    POSITIVE LOGITS
    Rid
    0.64
     rid
    0.56
     Rid
    0.53
     RID
    0.49
     ridd
    0.43
    Ridge
    0.43
    𝗈
    0.42
     crossroads
    0.41
     Ridg
    0.41
     Ridley
    0.40
    Activations Density 0.008%

    No Known Activations