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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     rém
    1.76
     (‘
    1.69
     Vee
    1.61
    囝
    1.58
     lawe
    1.57
    сле
    1.56
    貽
    1.56
     ihres
    1.53
    비를
    1.52
    =$\
    1.52
    POSITIVE LOGITS
     superficie
    1.70
     superficies
    1.68
    rinsic
    1.67
    thickness
    1.57
    7
    1.53
     powierzchn
    1.52
     powierzchni
    1.51
     сути
    1.49
     Germain
    1.46
     beton
    1.46
    Activations Density 0.671%

    No Known Activations