© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4027
    Prev
    Next
    INDEX
    Explanations

    provide a

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     occupants
    1.71
     Niño
    1.66
     descending
    1.65
     newborns
    1.65
     patern
    1.63
     infant
    1.61
    }°
    1.61
     resuscitation
    1.60
     infants
    1.60
     testosterone
    1.60
    POSITIVE LOGITS
    wig
    0.72
     Parse
    0.70
     Prag
    0.70
    orn
    0.69
    Parse
    0.67
    ファイ
    0.61
    が
    0.61
     casse
    0.60
    chek
    0.59
    wit
    0.58
    Activations Density 0.064%

    No Known Activations