© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    do not belong

    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
    촘
    0.59
     samoglas
    0.56
     वैश्विक
    0.54
    櫸
    0.54
    specifiedByURL
    0.53
    ״
    0.51
     perspici
    0.49
     groupby
    0.49
    idefinite
    0.48
    👫
    0.48
    POSITIVE LOGITS
     cyborg
    0.89
     undead
    0.88
     vampire
    0.86
     humanoid
    0.84
     assassin
    0.82
     mercenary
    0.81
     venge
    0.77
     dragon
    0.77
     samurai
    0.76
     assassins
    0.76
    Activations Density 0.414%

    No Known Activations