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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 227
    Prev
    Next
    INDEX
    Explanations

    and followed by descriptive words

    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
     Wasn
    1.18
    pillar
    1.14
    敍
    1.08
     platter
    1.06
     kej
    1.05
    }}>
    1.03
    intă
    1.02
     اقد
    1.01
    Референце
    1.00
     whichever
    0.99
    POSITIVE LOGITS
    much
    1.97
     bardzo
    1.97
    9
    1.94
    7
    1.90
    回事
    1.90
     علیکم
    1.89
     unterscheiden
    1.86
     cotid
    1.85
    ٩
    1.84
    窨
    1.83
    Activations Density 0.245%

    No Known Activations